StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling
cs.LG, cs.AI
Submitted: 2026-06-13
Updated: 2026-09-26
Comments: V2, preprint
Code: https://github.com/volcengine/verl
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling
- DeepSeek-V3 Technical Report
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learning
- ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling
- LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch
- Policy of Thoughts: Scaling Test-Time Training for LLM Reasoning via Online Policy Evolution
- Scalable Best-of-N Selection for Large Language Models via Self-Certainty
- SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search
- ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization
- Tool Verification for Test-Time Reinforcement Learning
- OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling
- GPT-4 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- Reflexion: Language Agents with Verbal Reinforcement Learning
- BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving
- ThetaEvolve: Test-time Learning on Open Problems
- Learning to Discover at Test Time
- SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks